A stopping rule for least-squares identification
Gang George Yin · IEEE Transactions on Automatic Control · 1989
A stopping rule for least-squares identification is developed. The stopping rule is determined by the construction of a confidence ellipsoid. For any predetermined estimation error epsilon >0, if the iterates are inside of an ellipsoidal confidence region with volume less than or equal to epsilon /sup r/, then the recursive online algorithm will be terminated with high probability.>